The role of social media in the stock market: twitter sentiment as a predictor of stock returns

• Autor(a) principal: Costa, Davide Gomes
• Data de Publicação: 2021
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10362/140471
• topic: Asset pricing; Big data; Sentiment analysis; Stock return; Investor sentiment; Domínio/Área Científica::Ciências Sociais::Economia e Gestão

The recent surge of emerging technologies, combined with the growth of social media securities-related microblogging, instigated academics to explore new proxies for sentiment. This research dissects the association between 1-month lagged Twitter sentiment and stock returns for the S&P500 constituents from 2008 to 2021 through the sentiment analysis of approximately 34.7million tweets. Evidence shows a consistent variation pattern of returns across the scope of the anomaly. Furthermore, abnormal returns associated with high Twitter sentiment are pervasive and significant, particularly for value-weight returns. In contrast, there is insufficient evidence on the pervasiveness of abnormal returns for low Twitter sentiment. Key words: Asset Pricing, Big Data, Sentiment Analysis, Stock Return, Investor Sentiment.